Skip to content
SPECIFICTION
Get listed

OmniSVG

omnisvg.net

Free plan WebmacOSLinuxSelf-hosted
Visit omnisvg.net
Spec score 7.9 #15 of 26 in AI Vector Generators

What it is

OmniSVG converts natural-language descriptions into scalable SVG graphics and can turn PNG, JPG, BMP, and WebP images into editable SVG. Image uploads are limited to 5 MB. Generated graphics can be previewed, downloaded, or copied as code for editing in an SVG-compatible tool. The free demo requires no account, shows the remaining daily generations in the browser, and allows five generations per day. The research project also supports image-to-SVG and character-reference SVG generation. It combines a pretrained Qwen-VL vision-language model with an SVG tokenizer and introduces MMSVG-2M, a dataset of two million annotated SVG assets. The code is licensed under Apache License 2.0. Local Gradio deployment instructions use Python 3.10, Cairo, and CUDA 12.1-tested dependencies. Listed model downloads range from 7.69 GB to 17.2 GB, with reported inference memory use of 17 GB for OmniSVG1.1_4B and 26 GB for OmniSVG1.1_8B. The project also lists an online demo and a community-contributed ComfyUI plugin.

Spec sheet

License
The OmniSVG code is licensed under Apache License 2.0.Read 30 Sep 2026 · github.com
Community integration
The repository lists a community-contributed ComfyUI OmniSVG plugin.Read 30 Sep 2026 · github.com
Dataset
The project introduces MMSVG-2M, a multimodal dataset containing two million richly annotated SVG assets.Read 30 Sep 2026 · omnisvg.github.io
Editing and export
Generated SVGs can be previewed, downloaded, or copied as code for editing in an SVG-compatible tool.Read 30 Sep 2026 · omnisvg.net
Generation modalities
The research project supports Text-to-SVG, Image-to-SVG, and Character-Reference SVG generation.Read 30 Sep 2026 · omnisvg.github.io
Image conversion
The image converter accepts PNG, JPG, BMP, and WebP files up to 5 MB and outputs editable SVG.Read 30 Sep 2026 · omnisvg.net
Local deployment
The repository provides local Gradio deployment and installation instructions using Python 3.10, Cairo, and CUDA 12.1-tested dependencies.Read 30 Sep 2026 · github.com
Model architecture
OmniSVG uses a pretrained Qwen-VL vision-language model together with an SVG tokenizer.Read 30 Sep 2026 · omnisvg.github.io
Model downloads
The repository lists OmniSVG1.1_8B at 17.2 GB, OmniSVG1.1_4B at 7.69 GB, and OmniSVG-3B at 8.49 GB.Read 30 Sep 2026 · github.com
No account
The free demo does not require an account and displays the remaining daily generations in the browser.Read 30 Sep 2026 · omnisvg.net
Online demo
The repository links to an online Hugging Face Spaces demo.Read 30 Sep 2026 · github.com
Performance limit
The repository reports 26 GB GPU memory usage for OmniSVG1.1_8B inference and 17 GB for OmniSVG1.1_4B.Read 30 Sep 2026 · github.com
Project affiliations
The project lists Fudan University and StepFun as the authors’ affiliations.Read 30 Sep 2026 · omnisvg.github.io
Text generation
OmniSVG converts natural-language descriptions into clean, scalable SVG graphics.Read 30 Sep 2026 · omnisvg.net
Use cases
The site lists web developers, UI/UX designers, content creators, and print or merchandise users as target audiences.Read 30 Sep 2026 · omnisvg.net

Plans and prices

Free Free Free demo; no account required 5 free generations per day · image uploads up to 5 MB Read 30 Sep 2026 · omnisvg.net

Every OmniSVG plan and price →

Strong points and limits

Strong points

  • Free demo requires no account
  • Creates SVG from text and supported images
  • Generated SVG can be downloaded or copied as code
  • Code is licensed under Apache License 2.0

Limits

  • Free demo allows five generations per day
  • Image uploads are limited to 5 MB
  • OmniSVG1.1_8B inference reports 26 GB GPU memory use

Who it suits

OmniSVG suits designers and creators who need editable SVGs from text or supported image files. Local deployment may interest users prepared to work with the listed software dependencies and model files.

Verdict

OmniSVG offers a no-account demo for generating and converting editable SVG graphics, alongside local deployment options. Daily generation and image-size limits matter for demo users, while local model use has substantial listed memory requirements.

Where Specifiction places it

Alternatives to OmniSVGAll alternatives →